Democratising design through surrogate model convolutional neural networks of computer aided design repositories

James Gopsill; Sean Jennings

Democratising design through surrogate model convolutional neural networks of computer aided design repositories

James Gopsill, Sean Jennings

Department of Mechanical Engineering

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

52 Downloads (Pure)

Abstract

The capability to manufacture at home is continually increasing with technologies, such as 3D printing. However, the ability to design products suitable for manufacture and use remains a highly-skilled and knowledge intensive activity. This has led to ‘content creators’ providing vast repositories of manufacturable products for society, however challenges remain in the search & retrieval of models. This paper presents the surrogate model convolutional neural networks approach to search and retrieve CAD models by mapping them directly to their real-world photographed counterparts.

Original language	English
Title of host publication	International Conference on DESIGN
Publication status	Acceptance date - 11 Feb 2020

Access to Document

mainAccepted author manuscript, 15.4 MB

RCUK Catapult Researchers in Residence (High Value Manufacturing NCC) - Valuing Digital Knowledge Assets within the High-Value Manufacturing Catapult
Gopsill, J. (PI)
Engineering and Physical Sciences Research Council
1/04/18 → 31/03/20
Project: Research council
Platform: Designing the Future: Resilient Trans-Disciplinary Design Engineers
Newnes, L. (PI), Dhokia, V. (CoI), Flynn, J. (CoI), Gopsill, J. (CoI), McManus, M. (CoI), Mullineux, G. (CoI), Newman, S. (CoI), Shokrani Chaharsooghi, A. (CoI), Trask, R. (CoI), Essink, W. (Researcher) & Lattanzio, S. (Researcher)
Engineering and Physical Sciences Research Council
1/12/17 → 31/08/23
Project: Research council

Cite this

@inproceedings{1da6c9ebb80240eebd10ac4ca77bd9c6,

title = "Democratising design through surrogate model convolutional neural networks of computer aided design repositories",

abstract = "The capability to manufacture at home is continually increasing with technologies, such as 3D printing. However, the ability to design products suitable for manufacture and use remains a highly-skilled and knowledge intensive activity. This has led to {\textquoteleft}content creators{\textquoteright} providing vast repositories of manufacturable products for society, however challenges remain in the search & retrieval of models. This paper presents the surrogate model convolutional neural networks approach to search and retrieve CAD models by mapping them directly to their real-world photographed counterparts.",

author = "James Gopsill and Sean Jennings",

year = "2020",

month = feb,

day = "11",

language = "English",

booktitle = "International Conference on DESIGN",

}

TY - GEN

T1 - Democratising design through surrogate model convolutional neural networks of computer aided design repositories

AU - Gopsill, James

AU - Jennings, Sean

PY - 2020/2/11

Y1 - 2020/2/11

N2 - The capability to manufacture at home is continually increasing with technologies, such as 3D printing. However, the ability to design products suitable for manufacture and use remains a highly-skilled and knowledge intensive activity. This has led to ‘content creators’ providing vast repositories of manufacturable products for society, however challenges remain in the search & retrieval of models. This paper presents the surrogate model convolutional neural networks approach to search and retrieve CAD models by mapping them directly to their real-world photographed counterparts.

AB - The capability to manufacture at home is continually increasing with technologies, such as 3D printing. However, the ability to design products suitable for manufacture and use remains a highly-skilled and knowledge intensive activity. This has led to ‘content creators’ providing vast repositories of manufacturable products for society, however challenges remain in the search & retrieval of models. This paper presents the surrogate model convolutional neural networks approach to search and retrieve CAD models by mapping them directly to their real-world photographed counterparts.

M3 - Chapter in a published conference proceeding

BT - International Conference on DESIGN

ER -

Democratising design through surrogate model convolutional neural networks of computer aided design repositories

Abstract

Access to Document

Fingerprint

Projects

RCUK Catapult Researchers in Residence (High Value Manufacturing NCC) - Valuing Digital Knowledge Assets within the High-Value Manufacturing Catapult

Platform: Designing the Future: Resilient Trans-Disciplinary Design Engineers

Cite this